Decoding three-dimensional trajectory of executed and imagined arm movements from electroencephalogram signals

Jeong Hun Kim, Felix Bießmann, Seong Whan Lee

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Decoding motor commands from noninvasively measured neural signals has become important in brain-computer interface (BCI) research. Applications of BCI include neurorehabilitation after stroke and control of limb prostheses. Until now, most studies have tested simple movement trajectories in two dimensions by using constant velocity profiles. However, most real-world scenarios require much more complex movement trajectories and velocity profiles. In this study, we decoded motor commands in three dimensions from electroencephalography (EEG) recordings while the subjects either executed or observed/imagined complex upper limb movement trajectories. We compared the accuracy of simple linear methods and nonlinear methods. In line with previous studies our results showed that linear decoders are an efficient and robust method for decoding motor commands. However, while we took the same precautions as previous studies to suppress eye-movement related EEG contamination, we found that subtracting residual electro-oculogram activity from the EEG data resulted in substantially lower motor decoding accuracy for linear decoders. This effect severely limits the transfer of previous results to practical applications in which neural activation is targeted. We observed that nonlinear methods showed no such drop in decoding performance. Our results demonstrate that eye-movement related contamination of brain signals constitutes a severe problem for decoding motor signals from EEG data. These results are important for developing accurate decoders of motor signal from neural signals for use with BCI-based neural prostheses and neurorehabilitation in real-world scenarios.

Original languageEnglish
Article number6971116
Pages (from-to)867-876
Number of pages10
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume23
Issue number5
DOIs
Publication statusPublished - 2015 Sep 1

Fingerprint

Electroencephalography
Brain-Computer Interfaces
Decoding
Arm
Trajectories
Brain computer interface
Eye Movements
Neural Prostheses
Eye movements
Artificial Limbs
Contamination
Neural prostheses
Upper Extremity
Stroke
Prosthetics
Brain
Chemical activation
Research
Neurological Rehabilitation

Keywords

  • Arm movement trajectory
  • Brain-computer interfaces (BCI)
  • Electroencephalography (EEG)
  • Kernel ridge regression
  • Upper limb rehabilitation

ASJC Scopus subject areas

  • Neuroscience(all)
  • Computer Science Applications
  • Biomedical Engineering

Cite this

Decoding three-dimensional trajectory of executed and imagined arm movements from electroencephalogram signals. / Kim, Jeong Hun; Bießmann, Felix; Lee, Seong Whan.

In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 23, No. 5, 6971116, 01.09.2015, p. 867-876.

Research output: Contribution to journalArticle

@article{cd3190958fb9467786cd425aa332daf6,
title = "Decoding three-dimensional trajectory of executed and imagined arm movements from electroencephalogram signals",
abstract = "Decoding motor commands from noninvasively measured neural signals has become important in brain-computer interface (BCI) research. Applications of BCI include neurorehabilitation after stroke and control of limb prostheses. Until now, most studies have tested simple movement trajectories in two dimensions by using constant velocity profiles. However, most real-world scenarios require much more complex movement trajectories and velocity profiles. In this study, we decoded motor commands in three dimensions from electroencephalography (EEG) recordings while the subjects either executed or observed/imagined complex upper limb movement trajectories. We compared the accuracy of simple linear methods and nonlinear methods. In line with previous studies our results showed that linear decoders are an efficient and robust method for decoding motor commands. However, while we took the same precautions as previous studies to suppress eye-movement related EEG contamination, we found that subtracting residual electro-oculogram activity from the EEG data resulted in substantially lower motor decoding accuracy for linear decoders. This effect severely limits the transfer of previous results to practical applications in which neural activation is targeted. We observed that nonlinear methods showed no such drop in decoding performance. Our results demonstrate that eye-movement related contamination of brain signals constitutes a severe problem for decoding motor signals from EEG data. These results are important for developing accurate decoders of motor signal from neural signals for use with BCI-based neural prostheses and neurorehabilitation in real-world scenarios.",
keywords = "Arm movement trajectory, Brain-computer interfaces (BCI), Electroencephalography (EEG), Kernel ridge regression, Upper limb rehabilitation",
author = "Kim, {Jeong Hun} and Felix Bie{\ss}mann and Lee, {Seong Whan}",
year = "2015",
month = "9",
day = "1",
doi = "10.1109/TNSRE.2014.2375879",
language = "English",
volume = "23",
pages = "867--876",
journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",
issn = "1534-4320",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Decoding three-dimensional trajectory of executed and imagined arm movements from electroencephalogram signals

AU - Kim, Jeong Hun

AU - Bießmann, Felix

AU - Lee, Seong Whan

PY - 2015/9/1

Y1 - 2015/9/1

N2 - Decoding motor commands from noninvasively measured neural signals has become important in brain-computer interface (BCI) research. Applications of BCI include neurorehabilitation after stroke and control of limb prostheses. Until now, most studies have tested simple movement trajectories in two dimensions by using constant velocity profiles. However, most real-world scenarios require much more complex movement trajectories and velocity profiles. In this study, we decoded motor commands in three dimensions from electroencephalography (EEG) recordings while the subjects either executed or observed/imagined complex upper limb movement trajectories. We compared the accuracy of simple linear methods and nonlinear methods. In line with previous studies our results showed that linear decoders are an efficient and robust method for decoding motor commands. However, while we took the same precautions as previous studies to suppress eye-movement related EEG contamination, we found that subtracting residual electro-oculogram activity from the EEG data resulted in substantially lower motor decoding accuracy for linear decoders. This effect severely limits the transfer of previous results to practical applications in which neural activation is targeted. We observed that nonlinear methods showed no such drop in decoding performance. Our results demonstrate that eye-movement related contamination of brain signals constitutes a severe problem for decoding motor signals from EEG data. These results are important for developing accurate decoders of motor signal from neural signals for use with BCI-based neural prostheses and neurorehabilitation in real-world scenarios.

AB - Decoding motor commands from noninvasively measured neural signals has become important in brain-computer interface (BCI) research. Applications of BCI include neurorehabilitation after stroke and control of limb prostheses. Until now, most studies have tested simple movement trajectories in two dimensions by using constant velocity profiles. However, most real-world scenarios require much more complex movement trajectories and velocity profiles. In this study, we decoded motor commands in three dimensions from electroencephalography (EEG) recordings while the subjects either executed or observed/imagined complex upper limb movement trajectories. We compared the accuracy of simple linear methods and nonlinear methods. In line with previous studies our results showed that linear decoders are an efficient and robust method for decoding motor commands. However, while we took the same precautions as previous studies to suppress eye-movement related EEG contamination, we found that subtracting residual electro-oculogram activity from the EEG data resulted in substantially lower motor decoding accuracy for linear decoders. This effect severely limits the transfer of previous results to practical applications in which neural activation is targeted. We observed that nonlinear methods showed no such drop in decoding performance. Our results demonstrate that eye-movement related contamination of brain signals constitutes a severe problem for decoding motor signals from EEG data. These results are important for developing accurate decoders of motor signal from neural signals for use with BCI-based neural prostheses and neurorehabilitation in real-world scenarios.

KW - Arm movement trajectory

KW - Brain-computer interfaces (BCI)

KW - Electroencephalography (EEG)

KW - Kernel ridge regression

KW - Upper limb rehabilitation

UR - http://www.scopus.com/inward/record.url?scp=84949971025&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949971025&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2014.2375879

DO - 10.1109/TNSRE.2014.2375879

M3 - Article

C2 - 25474811

AN - SCOPUS:84949971025

VL - 23

SP - 867

EP - 876

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1534-4320

IS - 5

M1 - 6971116

ER -